End of training

README.md

@@ -7,7 +7,6 @@ datasets:
 model-index:
 - name: tweet-summarization-llama-2-finetuned
   results: []
-pipeline_tag: text-generation
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -17,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) on the Salesforce/dialogstudio dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.9075
+- Loss: 1.8672
 
 ## Model description
 
@@ -45,14 +44,19 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_ratio: 0.05
-- num_epochs: 2
+- num_epochs: 7
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 1.9022        | 1.0   | 55   | 1.9515          |
-| 1.8691        | 2.0   | 110  | 1.9075          |
+| 1.8996        | 1.0   | 55   | 1.9491          |
+| 1.8415        | 2.0   | 110  | 1.8857          |
+| 1.7693        | 3.0   | 165  | 1.8749          |
+| 1.7136        | 4.0   | 220  | 1.8678          |
+| 1.7533        | 5.0   | 275  | 1.8663          |
+| 1.6182        | 6.0   | 330  | 1.8665          |
+| 1.69          | 7.0   | 385  | 1.8672          |
 
 
 ### Framework versions
@@ -60,4 +64,4 @@ The following hyperparameters were used during training:
 - Transformers 4.32.1
 - Pytorch 2.0.1+cu117
 - Datasets 2.14.4
-- Tokenizers 0.13.3
+- Tokenizers 0.13.3

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e08fef12106f8e85735ac0ddf86165890b40cadf268a25da77bc6c0a69ea40e
+oid sha256:652bc9e3624b3beceebcc5f60311ac77d76fc76eae0643651475538b8324f3ee
 size 33571624